{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "Step 1: Importing Required Libraries"
      ],
      "metadata": {
        "id": "k3iSjuNTF4Og"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "1Jcsk7bwvvPB"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "import matplotlib.pyplot as plt\n",
        "import zipfile\n",
        "import os\n",
        "\n",
        "from tensorflow.keras import layers\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.applications import EfficientNetB0"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 2: Mounting Google Drive"
      ],
      "metadata": {
        "id": "S7BDjSorF61r"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TDwYkwzog4Zy",
        "outputId": "4671c7e9-8a03-4ef4-d953-b676383dae6d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 3: Searching for the Dataset ZIP File"
      ],
      "metadata": {
        "id": "uyDnAWfmF_ar"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "S2Am_ncdFvwE"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "\n",
        "for root, dirs, files in os.walk(\"/content\"):\n",
        "    for file in files:\n",
        "        if file.endswith(\".zip\"):\n",
        "            print(os.path.join(root, file))"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 4: Uploading the Dataset"
      ],
      "metadata": {
        "id": "fHfHhC5bGDTk"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "rHNQaPIKhY_N",
        "outputId": "1cceba71-1a47-477d-b874-612534ec3e48"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-c6d0083f-9602-4fdc-9574-bca1f5e64f92\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-c6d0083f-9602-4fdc-9574-bca1f5e64f92\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving PlantPathology_Split.zip to PlantPathology_Split.zip\n"
          ]
        }
      ],
      "source": [
        "from google.colab import files\n",
        "\n",
        "uploaded = files.upload()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 5: Extracting the Dataset"
      ],
      "metadata": {
        "id": "uqbghiL9GHAe"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4CswI5BtGEcL",
        "outputId": "fc29e961-269a-4ef0-d5f1-9fc85a051349"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extraction completed!\n"
          ]
        }
      ],
      "source": [
        "import zipfile\n",
        "import os\n",
        "\n",
        "zip_file = \"/content/PlantPathology_Split.zip\"\n",
        "extract_path = \"/content/PlantPathology_Split\"\n",
        "\n",
        "# Check if the zip file exists before attempting to extract\n",
        "if not os.path.exists(zip_file):\n",
        "    print(f\"Error: The specified zip file '{zip_file}' was not found.\")\n",
        "    print(\"Please ensure the file is uploaded to this path or update 'zip_file' with the correct path to your zip file.\")\n",
        "else:\n",
        "    with zipfile.ZipFile(zip_file, \"r\") as zip_ref:\n",
        "        zip_ref.extractall(extract_path)\n",
        "\n",
        "    print(\"Extraction completed!\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 6: Locating the Dataset Folder Structure"
      ],
      "metadata": {
        "id": "HCAEODFfGPmt"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YXFq2y_4GLGL",
        "outputId": "113e3e84-2a01-4afc-af5f-fd0baa8bb0b8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Dataset Path:\n",
            "/content/PlantPathology_Split/PlantPathology_Split\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "\n",
        "base_dir = None\n",
        "\n",
        "for root, dirs, files in os.walk(extract_path):\n",
        "\n",
        "    if \"train\" in dirs and \"valid\" in dirs and \"test\" in dirs:\n",
        "        base_dir = root\n",
        "        break\n",
        "\n",
        "print(\"Dataset Path:\")\n",
        "print(base_dir)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 7: Loading the Image Datasets"
      ],
      "metadata": {
        "id": "dmNuAoP3GT1S"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TUq88fqfGYAs",
        "outputId": "d0c524ae-f971-4519-ac7f-28055d0d4eb7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 8691 files belonging to 12 classes.\n",
            "Found 1862 files belonging to 12 classes.\n",
            "Found 1863 files belonging to 12 classes.\n",
            "['complex', 'frog_eye_leaf_spot', 'frog_eye_leaf_spot complex', 'healthy', 'powdery_mildew', 'powdery_mildew complex', 'rust', 'rust complex', 'rust frog_eye_leaf_spot', 'scab', 'scab frog_eye_leaf_spot', 'scab frog_eye_leaf_spot complex']\n",
            "Number of Classes = 12\n"
          ]
        }
      ],
      "source": [
        "IMG_SIZE = (224,224)\n",
        "\n",
        "BATCH_SIZE = 32\n",
        "\n",
        "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"train\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\"\n",
        "\n",
        ")\n",
        "\n",
        "valid_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"valid\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\"\n",
        "\n",
        ")\n",
        "\n",
        "test_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"test\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\",\n",
        "\n",
        "    shuffle=False\n",
        "\n",
        ")\n",
        "\n",
        "class_names = train_ds.class_names\n",
        "\n",
        "print(class_names)\n",
        "\n",
        "print(\"Number of Classes =\",len(class_names))"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 8: Optimising Data Loading Performance"
      ],
      "metadata": {
        "id": "J5fiUFtTGYDx"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "K7uXWkErGa0x"
      },
      "outputs": [],
      "source": [
        "AUTOTUNE = tf.data.AUTOTUNE\n",
        "\n",
        "train_ds = train_ds.cache().shuffle(1000).prefetch(AUTOTUNE)\n",
        "\n",
        "valid_ds = valid_ds.cache().prefetch(AUTOTUNE)\n",
        "\n",
        "test_ds = test_ds.cache().prefetch(AUTOTUNE)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 9: Data Augmentation"
      ],
      "metadata": {
        "id": "xD6TO_mQGcEp"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "H_I8vMhgGdsc"
      },
      "outputs": [],
      "source": [
        "data_augmentation = tf.keras.Sequential([\n",
        "\n",
        "    layers.RandomFlip(\"horizontal\"),\n",
        "\n",
        "    layers.RandomRotation(0.2),\n",
        "\n",
        "    layers.RandomZoom(0.2),\n",
        "\n",
        "    layers.RandomContrast(0.2),\n",
        "\n",
        "    layers.RandomTranslation(0.1,0.1),\n",
        "\n",
        "])"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 10: Loading the Pre-Trained EfficientNetB0 Base"
      ],
      "metadata": {
        "id": "4dwcpIRDGf2_"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "o_qzIIdlGnEx",
        "outputId": "80988907-439d-4c47-da3e-c02b2142363e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/keras-applications/efficientnetb0_notop.h5\n",
            "\u001b[1m16705208/16705208\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n",
            "EfficientNetB0 Loaded Successfully\n"
          ]
        }
      ],
      "source": [
        "base_model = EfficientNetB0(\n",
        "\n",
        "    include_top=False,\n",
        "\n",
        "    weights=\"imagenet\",\n",
        "\n",
        "    input_shape=(224,224,3)\n",
        "\n",
        ")\n",
        "\n",
        "base_model.trainable = False\n",
        "\n",
        "print(\"EfficientNetB0 Loaded Successfully\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 11: Building the Full Model Architecture"
      ],
      "metadata": {
        "id": "ci3iuL8SGoOl"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 502
        },
        "id": "APCfzCWAGoqz",
        "outputId": "9f4a82c5-7e88-4a36-da03-2592c710ac85"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"functional_1\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_1\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_1 (\u001b[38;5;33mInputLayer\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential (\u001b[38;5;33mSequential\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ efficientnetb0 (\u001b[38;5;33mFunctional\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m1280\u001b[0m)     │     \u001b[38;5;34m4,049,571\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1280\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n",
              "│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1280\u001b[0m)           │         \u001b[38;5;34m5,120\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │       \u001b[38;5;34m655,872\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m131,328\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m)             │         \u001b[38;5;34m3,084\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Sequential</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ efficientnetb0 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">7</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">7</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">4,049,571</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)           │         <span style=\"color: #00af00; text-decoration-color: #00af00\">5,120</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">655,872</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">131,328</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">3,084</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,844,975\u001b[0m (18.48 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,844,975</span> (18.48 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m792,844\u001b[0m (3.02 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">792,844</span> (3.02 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m4,052,131\u001b[0m (15.46 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,052,131</span> (15.46 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ],
      "source": [
        "inputs = tf.keras.Input(shape=(224,224,3))\n",
        "\n",
        "x = data_augmentation(inputs)\n",
        "\n",
        "x = tf.keras.applications.efficientnet.preprocess_input(x)\n",
        "\n",
        "x = base_model(x, training=False)\n",
        "\n",
        "x = layers.GlobalAveragePooling2D()(x)\n",
        "\n",
        "x = layers.BatchNormalization()(x)\n",
        "\n",
        "x = layers.Dense(512, activation=\"relu\")(x)\n",
        "\n",
        "x = layers.Dropout(0.5)(x)\n",
        "\n",
        "x = layers.Dense(256, activation=\"relu\")(x)\n",
        "\n",
        "x = layers.Dropout(0.3)(x)\n",
        "\n",
        "outputs = layers.Dense(len(class_names), activation=\"softmax\")(x)\n",
        "\n",
        "model = Model(inputs, outputs)\n",
        "\n",
        "model.summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 12: Compiling the Model"
      ],
      "metadata": {
        "id": "sDM8xHEhGqA8"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "id": "p9P6y6rJGsvX"
      },
      "outputs": [],
      "source": [
        "model.compile(\n",
        "\n",
        "    optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001),\n",
        "\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "\n",
        "    metrics=[\"accuracy\"]\n",
        "\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 13: Setting Up Training Callbacks"
      ],
      "metadata": {
        "id": "tQRJhDdeGtcY"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "id": "DpQsjG4IGwwT"
      },
      "outputs": [],
      "source": [
        "early_stop = tf.keras.callbacks.EarlyStopping(\n",
        "\n",
        "    monitor=\"val_loss\",\n",
        "\n",
        "    patience=5,\n",
        "\n",
        "    restore_best_weights=True\n",
        "\n",
        ")\n",
        "\n",
        "reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n",
        "\n",
        "    monitor=\"val_loss\",\n",
        "\n",
        "    factor=0.2,\n",
        "\n",
        "    patience=2,\n",
        "\n",
        "    min_lr=1e-6,\n",
        "\n",
        "    verbose=1\n",
        "\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 14: Initial Training (Feature Extraction Phase)"
      ],
      "metadata": {
        "id": "4qkivNgfGw6_"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eJCqG4PXRo7u",
        "outputId": "656cff8c-b635-4884-9595-424da496bcca"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m871s\u001b[0m 3s/step - accuracy: 0.3577 - loss: 2.0152 - val_accuracy: 0.5832 - val_loss: 1.4070 - learning_rate: 1.0000e-04\n",
            "Epoch 2/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m814s\u001b[0m 3s/step - accuracy: 0.4960 - loss: 1.5645 - val_accuracy: 0.6369 - val_loss: 1.1685 - learning_rate: 1.0000e-04\n",
            "Epoch 3/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m822s\u001b[0m 3s/step - accuracy: 0.5339 - loss: 1.4117 - val_accuracy: 0.6504 - val_loss: 1.1054 - learning_rate: 1.0000e-04\n",
            "Epoch 4/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m820s\u001b[0m 3s/step - accuracy: 0.5561 - loss: 1.3394 - val_accuracy: 0.6697 - val_loss: 1.0471 - learning_rate: 1.0000e-04\n",
            "Epoch 5/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m818s\u001b[0m 3s/step - accuracy: 0.5835 - loss: 1.2809 - val_accuracy: 0.6810 - val_loss: 1.0327 - learning_rate: 1.0000e-04\n",
            "Epoch 6/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m831s\u001b[0m 3s/step - accuracy: 0.5964 - loss: 1.2300 - val_accuracy: 0.6890 - val_loss: 0.9907 - learning_rate: 1.0000e-04\n",
            "Epoch 7/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m850s\u001b[0m 3s/step - accuracy: 0.6057 - loss: 1.2056 - val_accuracy: 0.6907 - val_loss: 0.9857 - learning_rate: 1.0000e-04\n",
            "Epoch 8/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m815s\u001b[0m 3s/step - accuracy: 0.6187 - loss: 1.1678 - val_accuracy: 0.6939 - val_loss: 0.9725 - learning_rate: 1.0000e-04\n",
            "Epoch 9/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m889s\u001b[0m 3s/step - accuracy: 0.6301 - loss: 1.1445 - val_accuracy: 0.7009 - val_loss: 0.9484 - learning_rate: 1.0000e-04\n",
            "Epoch 10/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m848s\u001b[0m 3s/step - accuracy: 0.6387 - loss: 1.1189 - val_accuracy: 0.7057 - val_loss: 0.9421 - learning_rate: 1.0000e-04\n",
            "Epoch 11/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m823s\u001b[0m 3s/step - accuracy: 0.6417 - loss: 1.0938 - val_accuracy: 0.6853 - val_loss: 0.9708 - learning_rate: 1.0000e-04\n",
            "Epoch 12/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.6462 - loss: 1.0942\n",
            "Epoch 12: ReduceLROnPlateau reducing learning rate to 1.9999999494757503e-05.\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m822s\u001b[0m 3s/step - accuracy: 0.6440 - loss: 1.0931 - val_accuracy: 0.6890 - val_loss: 0.9704 - learning_rate: 1.0000e-04\n",
            "Epoch 13/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m883s\u001b[0m 3s/step - accuracy: 0.6508 - loss: 1.0722 - val_accuracy: 0.6971 - val_loss: 0.9514 - learning_rate: 2.0000e-05\n",
            "Epoch 14/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.6466 - loss: 1.0787\n",
            "Epoch 14: ReduceLROnPlateau reducing learning rate to 3.999999898951501e-06.\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m845s\u001b[0m 3s/step - accuracy: 0.6462 - loss: 1.0750 - val_accuracy: 0.6960 - val_loss: 0.9520 - learning_rate: 2.0000e-05\n",
            "Epoch 15/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m822s\u001b[0m 3s/step - accuracy: 0.6577 - loss: 1.0549 - val_accuracy: 0.7035 - val_loss: 0.9479 - learning_rate: 4.0000e-06\n"
          ]
        }
      ],
      "source": [
        "history = model.fit(\n",
        "\n",
        "    train_ds,\n",
        "\n",
        "    validation_data=valid_ds,\n",
        "\n",
        "    epochs=15,\n",
        "\n",
        "    callbacks=[early_stop, reduce_lr]\n",
        "\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 15: Unfreezing Layers for Fine-Tuning"
      ],
      "metadata": {
        "id": "LrL-lGBWG04z"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "juMCM7PVG1IT",
        "outputId": "4263bcc4-f9bb-4de2-f4d8-f16a1a854f44"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fine-tuning last 30 layers...\n"
          ]
        }
      ],
      "source": [
        "# Unfreeze the base model\n",
        "base_model.trainable = True\n",
        "\n",
        "# Freeze all layers except the last 30\n",
        "for layer in base_model.layers[:-30]:\n",
        "    layer.trainable = False\n",
        "\n",
        "print(\"Fine-tuning last 30 layers...\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 16: Recompiling the Model with a Lower Learning Rate"
      ],
      "metadata": {
        "id": "Rd6lU76FHDky"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "id": "8T92U1KlI3Tm"
      },
      "outputs": [],
      "source": [
        "model.compile(\n",
        "    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-5),\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 17: Fine-Tuning and Evaluating the Model"
      ],
      "metadata": {
        "id": "tc4N_VY2HH6s"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7ks5LKMBI4zo",
        "outputId": "6e9b8060-ddc4-43ef-9112-8afaa4510a23"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m959s\u001b[0m 3s/step - accuracy: 0.4926 - loss: 1.5007 - val_accuracy: 0.6649 - val_loss: 1.0588 - learning_rate: 1.0000e-05\n",
            "Epoch 2/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.5392 - loss: 1.3998\n",
            "Epoch 2: ReduceLROnPlateau reducing learning rate to 1.9999999494757505e-06.\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m929s\u001b[0m 3s/step - accuracy: 0.5375 - loss: 1.3910 - val_accuracy: 0.6713 - val_loss: 1.0349 - learning_rate: 1.0000e-05\n",
            "Epoch 3/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m936s\u001b[0m 3s/step - accuracy: 0.5541 - loss: 1.3439 - val_accuracy: 0.6772 - val_loss: 1.0285 - learning_rate: 2.0000e-06\n",
            "Epoch 4/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.5517 - loss: 1.3549\n",
            "Epoch 4: ReduceLROnPlateau reducing learning rate to 1e-06.\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m927s\u001b[0m 3s/step - accuracy: 0.5653 - loss: 1.3267 - val_accuracy: 0.6778 - val_loss: 1.0205 - learning_rate: 2.0000e-06\n",
            "Epoch 5/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m955s\u001b[0m 4s/step - accuracy: 0.5669 - loss: 1.3147 - val_accuracy: 0.6799 - val_loss: 1.0135 - learning_rate: 1.0000e-06\n",
            "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m127s\u001b[0m 2s/step - accuracy: 0.6683 - loss: 1.0352\n",
            "Test Accuracy: 0.6682769656181335\n"
          ]
        }
      ],
      "source": [
        "history = model.fit(\n",
        "    train_ds,\n",
        "    validation_data=valid_ds,\n",
        "    epochs=15,\n",
        "    callbacks=[early_stop, reduce_lr]\n",
        ")\n",
        "\n",
        "test_loss, test_accuracy = model.evaluate(test_ds)\n",
        "\n",
        "print(\"Test Accuracy:\", test_accuracy)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 18: Plotting Accuracy and Loss Curves"
      ],
      "metadata": {
        "id": "lx7WkrZWHMIJ"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "LbRQm6sTI6X_",
        "outputId": "c7c5b381-73f9-499e-c5eb-7304df23437d"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.figure(figsize=(14,5))\n",
        "\n",
        "# Accuracy\n",
        "plt.subplot(1,2,1)\n",
        "plt.plot(history.history['accuracy'], marker='o')\n",
        "plt.plot(history.history['val_accuracy'], marker='o')\n",
        "plt.title(\"Model Accuracy\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.legend([\"Training Accuracy\",\"Validation Accuracy\"])\n",
        "\n",
        "# Loss\n",
        "plt.subplot(1,2,2)\n",
        "plt.plot(history.history['loss'], marker='o')\n",
        "plt.plot(history.history['val_loss'], marker='o')\n",
        "plt.title(\"Model Loss\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Loss\")\n",
        "plt.legend([\"Training Loss\",\"Validation Loss\"])\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 18: Plotting Accuracy and Loss Curves"
      ],
      "metadata": {
        "id": "mzsIQPHGHQmB"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HdWvYCBHOWHs",
        "outputId": "01bb0116-ece4-4d6b-98bc-eb6bcc04c4e0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m126s\u001b[0m 2s/step\n"
          ]
        }
      ],
      "source": [
        "import numpy as np\n",
        "\n",
        "y_true = np.concatenate([y for x, y in test_ds], axis=0)\n",
        "\n",
        "predictions = model.predict(test_ds)\n",
        "\n",
        "y_pred = np.argmax(predictions, axis=1)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 20: Classification Report"
      ],
      "metadata": {
        "id": "gBx3rbzfHTzv"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vSONP-P-OaiY",
        "outputId": "92efae95-0b10-486e-a762-fa8ff545b714"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "                                 precision    recall  f1-score   support\n",
            "\n",
            "                        complex       0.37      0.25      0.30       160\n",
            "             frog_eye_leaf_spot       0.54      0.73      0.62       310\n",
            "     frog_eye_leaf_spot complex       0.00      0.00      0.00        16\n",
            "                        healthy       0.81      0.82      0.82       445\n",
            "                 powdery_mildew       0.85      0.79      0.82       126\n",
            "         powdery_mildew complex       0.00      0.00      0.00         8\n",
            "                           rust       0.61      0.69      0.65       186\n",
            "                   rust complex       0.00      0.00      0.00         9\n",
            "        rust frog_eye_leaf_spot       0.00      0.00      0.00        13\n",
            "                           scab       0.70      0.77      0.73       500\n",
            "        scab frog_eye_leaf_spot       0.09      0.01      0.02        73\n",
            "scab frog_eye_leaf_spot complex       0.00      0.00      0.00        17\n",
            "\n",
            "                       accuracy                           0.67      1863\n",
            "                      macro avg       0.33      0.34      0.33      1863\n",
            "                   weighted avg       0.63      0.67      0.64      1863\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
          ]
        }
      ],
      "source": [
        "from sklearn.metrics import classification_report\n",
        "\n",
        "print(classification_report(\n",
        "    y_true,\n",
        "    y_pred,\n",
        "    target_names=class_names\n",
        "))"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 21: Confusion Matrix Visualisation"
      ],
      "metadata": {
        "id": "-gu7wl9bHXol"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 934
        },
        "id": "bmUrs03gOfl_",
        "outputId": "eac6558a-ca04-4f07-98e0-f47976784791"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "from sklearn.metrics import confusion_matrix\n",
        "import seaborn as sns\n",
        "\n",
        "cm = confusion_matrix(y_true, y_pred)\n",
        "\n",
        "plt.figure(figsize=(10,8))\n",
        "\n",
        "sns.heatmap(\n",
        "    cm,\n",
        "    annot=True,\n",
        "    fmt='d',\n",
        "    cmap='Blues',\n",
        "    xticklabels=class_names,\n",
        "    yticklabels=class_names\n",
        ")\n",
        "\n",
        "plt.xlabel(\"Predicted\")\n",
        "plt.ylabel(\"Actual\")\n",
        "plt.title(\"Confusion Matrix\")\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 22: Saving the Trained Model"
      ],
      "metadata": {
        "id": "OIzqYzdFHbwK"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y7CvkD2dOoI2",
        "outputId": "f711e0ba-a9d2-4ea0-a190-566fc15a1486"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model Saved Successfully to Google Drive!\n"
          ]
        }
      ],
      "source": [
        "model.save(\"/content/drive/My Drive/Plant_Disease_EfficientNetB0.keras\")\n",
        "\n",
        "print(\"Model Saved Successfully to Google Drive!\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Step 23: Exporting the Training History"
      ],
      "metadata": {
        "id": "v1IrSdmvHe_5"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4k1RtpO_Ouyk",
        "outputId": "bc0946c0-458f-4047-ef0f-3e00958b3192"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "   accuracy      loss  val_accuracy  val_loss  learning_rate\n",
            "0  0.492579  1.500717      0.664876  1.058827   1.000000e-05\n",
            "1  0.537453  1.390969      0.671321  1.034945   1.000000e-05\n",
            "2  0.554136  1.343874      0.677229  1.028511   2.000000e-06\n",
            "3  0.565297  1.326727      0.677766  1.020482   2.000000e-06\n",
            "4  0.566908  1.314698      0.679914  1.013497   1.000000e-06\n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "\n",
        "history_df = pd.DataFrame(history.history)\n",
        "\n",
        "history_df.to_csv(\"training_history.csv\", index=False)\n",
        "\n",
        "print(history_df.head())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "j9NZ_0rsOx70"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}